Artificial intelligence for precision medicine in neurodevelopmental disorders.

The ambition of precision medicine is to design and optimize the pathway for diagnosis, therapeutic intervention, and prognosis by using large multidimensional biological datasets that capture individual variability in genes, function and environment. This offers clinicians the opportunity to more carefully tailor early interventions- whether treatment or preventative in nature-to each individual patient. Taking advantage of high performance computer capabilities, artificial intelligence (AI) algorithms can now achieve reasonable success in predicting risk in certain cancers and cardiovascular disease from available multidimensional clinical and biological data. In contrast, less progress has been made with the neurodevelopmental disorders, which include intellectual disability (ID), autism spectrum disorder (ASD), epilepsy and broader neurodevelopmental disorders. Much hope is pinned on the opportunity to quantify risk from patterns of genomic variation, including the functional characterization of genes and variants, but this ambition is confounded by phenotypic and etiologic heterogeneity, along with the rare and variable penetrant nature of the underlying risk variants identified so far. Structural and functional brain imaging and neuropsychological and neurophysiological markers may provide further dimensionality, but often require more development to achieve sensitivity for diagnosis. Herein, therefore, lies a precision medicine conundrum: can artificial intelligence offer a breakthrough in predicting risks and prognosis for neurodevelopmental disorders? In this review we will examine these complexities, and consider some of the strategies whereby artificial intelligence may overcome them.

Novel mutations in actionable breast cancer genes by targeted sequencing in an ethnically homogenous cohort.

BACKGROUND: Genetic testing is becoming an essential tool for breast cancer (BC) diagnosis and treatment pathway, and particularly important for early detection and cancer prevention. The purpose of this study was to explore the diagnostic yield of targeted sequencing of the high priority BC genes. METHODS: We have utilized a cost-effective targeted sequencing approach of high priority actionable BC genes (BRCA1, BRCA2, ERBB2 and TP53) in a homogeneous patient cohort from Bangladesh (n = 52) by using tumor and blood samples. RESULTS: Blood derived targeted sequencing revealed 25.58% (11/43) clinically relevant mutations (both pathogenic and variants of uncertain significance (VUS)), with 13.95% (6/43) of samples carrying a pathogenic mutations. We have identified and validated five novel pathogenic germline mutations in this cohort, comprising of two frameshift deletions in BRCA2, and missense mutations in BRCA1, BRCA2 and ERBB2 gene respectively. Furthermore, we have identified three pathogenic mutations and a VUS within three tumor samples, including a sample carrying pathogenic mutations impacting both TP53 (c.322dupG; a novel frameshift insertion) and BRCA1 genes (c.116G > A). 22% of tissue samples had a clinically relevant TP53 mutation. Although the cohort is small, we have found pathogenic mutations to be enriched in BRCA2 (9.30%, 4/43) compare to BRCA1 (4.65%, 2/43). The frequency of germline VUS mutations found to be similar in both BRCA1 (4.65%; 2/43) and BRCA2 (4.65%; 2/43) compared to ERBB2 (2.32%; 1/43). CONCLUSIONS: This is the first genetic study of BC predisposition genes in this population, implies that genetic screening through targeted sequencing can detect clinically significant and actionable BC-relevant mutations.

An ANKRD26 nonsense somatic mutation in a female with epidermodysplasia verruciformis (Tree Man Syndrome).

Epidermodysplasia verruciformis (EV) is an extremely rare hereditary skin disease characterized by an abnormal susceptibility to the human papilloma virus (HPV) with an increased risk of cutaneous malignancy. Here we report the first female severe EV case in Bangladesh, a 10-year-old girl with a nonsense somatic mutation impacting ANKRD26 gene.

Progress in the genetics of autism spectrum disorder.

A genetic basis for autism spectrum disorder (ASD) is now well established, and with the availability of high-throughput microarray and sequencing platforms, major advances have been made in our understanding of genetic risk factors. Rare, often de novo, copy number and single nucleotide variants are both implicated, with many ASD-implicated genes showing pleiotropy and variable penetrance. Additionally, common variants are also known to play a role in ASD's genetic etiology. These new insights into the architecture of ASD's genetic etiology offer opportunities for the identification of molecular targets for novel interventions, and provide new insight for families seeking genetic counselling. WHAT THE PAPER ADDS: A number of rare genetic variants are implicated in autism spectrum disorder (ASD), with some showing recurrence. Common genetic variants are also important and a number of loci are now being uncovered. Genetic testing for individuals with ASD offers the opportunity to identify relevant genetic etiology.

Germline and somatic mutations in STXBP1 with diverse neurodevelopmental phenotypes.

OBJECTIVE: To expand the clinical phenotype associated with STXBP1 gene mutations and to understand the effect of STXBP1 mutations in the pathogenesis of focal cortical dysplasia (FCD). METHODS: Patients with STXBP1 mutations were identified in various ways: as part of a retrospective cohort study of epileptic encephalopathy; through clinical referrals of individuals (10,619) with developmental delay (DD) for chromosomal microarray; and from a collection of 5,205 individuals with autism spectrum disorder (ASD) examined by whole-genome sequencing. RESULTS: Seven patients with heterozygous de novo mutations affecting the coding region of STXBP1 were newly identified. Three cases had radiologic evidence suggestive of FCD. One male patient with early infantile epileptic encephalopathy, DD, and ASD achieved complete seizure remission following resection of dysplastic brain tissue. Examination of excised brain tissue identified mosaicism for STXBP1, providing evidence for a somatic mechanism. Cell-type expression analysis suggested neuron-specific expression. A comprehensive analysis of the published data revealed that 3.1% of severe epilepsy cases carry a pathogenic de novo mutation within STXBP1. By contrast, ASD was rarely associated with mutations in this gene in our large cohorts. CONCLUSIONS: STXBP1 mutations are an important cause of epilepsy and are also rarely associated with ASD. In a case with histologically proven FCD, an STXBP1 somatic mutation was identified, suggesting a role in its etiology. Removing such tissue may be curative for STXBP1-related epilepsy.

The Adult Asperger Assessment (AAA): a diagnostic method.

At the present time there are a large number of adults who have suspected Asperger syndrome (AS). In this paper we describe a new instrument, the Adult Asperger Assessment (AAA), developed in our clinic for adults with AS. The need for a new instrument relevant to the diagnosis of AS in adulthood arises because existing instruments are designed for use with children. Properties of the AAA include (1) being electronic, data-based, and computer-scorable; (2) linking with two screening instruments [the Autism Spectrum Quotient (AQ) and the Empathy Quotient (EQ)]; and (3) employing a more stringent set of diagnostic criteria than DSM-IV, in order to avoid false positives. The AAA is described, and its use with a series of n = 42 clinic-patients is reported. Thirty-seven of these (88%) met DSM-IV criteria, but only 34 of these (80%) met AAA criteria. The AAA is therefore more conservative than DSM-IV.